The existing military fitness evaluation system has the defect of low accuracy, which cannot meet the needs of today's military field. Therefore, this paper puts forward the design and research of military physica...
详细信息
ISBN:
(纸本)9789811697357;9789811697340
The existing military fitness evaluation system has the defect of low accuracy, which cannot meet the needs of today's military field. Therefore, this paper puts forward the design and research of military physical fitness evaluation systems based on big data clustering algorithm. The big data clustering algorithm is introduced to design the military physical fitness evaluation system. The hardware unit is mainly the input unit, controller, arithmetic unit, memory, and output unit;the software module is mainly the construction module of the military physical fitness evaluation index system, the application module of big data clustering algorithm, and the database establishment module. Through the design of hardware unit and software module, the operation of the military physical fitness evaluation system is realized. The experimental results show that through data comparison, compared with the existing system, the design system has higher accuracy of military physical fitness evaluation results, which fully confirms the effectiveness and feasibility of the design system.
The rapid development of cloud computing technology has spawned many excellent cloud computing platforms. These cloud computing platforms provide an effective solution for the processing of bigdata, which can be used...
详细信息
The rapid development of cloud computing technology has spawned many excellent cloud computing platforms. These cloud computing platforms provide an effective solution for the processing of bigdata, which can be used as the basis for the study of parallel mining algorithms and the application of algorithms. This article uses the FP-Growth algorithm to mine and analyze computer bigdata. Aiming at the low extraction efficiency of traditional FP-Growth algorithm in large-scale data environment, an improved FP-Growth algorithm is proposed. In addition, in view of the shortcomings of frequent lists of L elements that are often cross-referenced in the FP-tree construction process, an improved algorithm based on hash tables is proposed, which realizes the storage address processing element name key, and then realizes the element name key to storage numbered mapping. This article mainly introduces the optimization of FP-Growth algorithm under the background of cloud computing and computer bigdata. The experimental results in this paper show that the performance of the improved FP-gtowth algorithm is better than the original algorithm, the traversal time is reduced by 13%, and the mining efficiency is increased by 25%. In addition, the use of this algorithm for dataclustering reduces the error rate and optimizes performance becomes better and has better application value.
暂无评论